diff options
author | Tom Lane <tgl@sss.pgh.pa.us> | 2020-07-14 18:56:49 -0400 |
---|---|---|
committer | Tom Lane <tgl@sss.pgh.pa.us> | 2020-07-14 18:56:56 -0400 |
commit | 689696c7110f148ede8004aae50d7543d05b5587 (patch) | |
tree | 852f7e573b2f66451a538aa347f5fc4734db6e35 /src/backend/optimizer/path/indxpath.c | |
parent | de8feb1f3a23465b5737e8a8c160e8ca62f61339 (diff) | |
download | postgresql-689696c7110f148ede8004aae50d7543d05b5587.tar.gz postgresql-689696c7110f148ede8004aae50d7543d05b5587.zip |
Fix bitmap AND/OR scans on the inside of a nestloop partition-wise join.
reparameterize_path_by_child() failed to reparameterize BitmapAnd
and BitmapOr paths. This matters only if such a path is chosen as
the inside of a nestloop partition-wise join, where we have to pass
in parameters from the outside of the nestloop. If that did happen,
we generated a bad plan that would likely lead to crashes at execution.
This is not entirely reparameterize_path_by_child()'s fault though;
it's the victim of an ancient decision (my ancient decision, I think)
to not bother filling in param_info in BitmapAnd/Or path nodes. That
caused the function to believe that such nodes and their children
contain no parameter references and so need not be processed.
In hindsight that decision looks pretty penny-wise and pound-foolish:
while it saves a few cycles during path node setup, we do commonly
need the information later. In particular, by reversing the decision
and requiring valid param_info data in all nodes of a bitmap path
tree, we can get rid of indxpath.c's get_bitmap_tree_required_outer()
function, which computed the data on-demand. It's not unlikely that
that nets out as a savings of cycles in many scenarios. A couple
of other things in indxpath.c can be simplified as well.
While here, get rid of some cases in reparameterize_path_by_child()
that are visibly dead or useless, given that we only care about
reparameterizing paths that can be on the inside of a parameterized
nestloop. This case reminds one of the maxim that untested code
probably does not work, so I'm unwilling to leave unreachable code
in this function. (I did leave the T_Gather case in place even
though it's not reached in the regression tests. It's not very
clear to me when the planner might prefer to put Gather below
rather than above a nestloop, but at least in principle the case
might be interesting.)
Per bug #16536, originally from Arne Roland but with a test case
by Andrew Gierth. Back-patch to v11 where this code came in.
Discussion: https://postgr.es/m/16536-2213ee0b3aad41fd@postgresql.org
Diffstat (limited to 'src/backend/optimizer/path/indxpath.c')
-rw-r--r-- | src/backend/optimizer/path/indxpath.c | 121 |
1 files changed, 17 insertions, 104 deletions
diff --git a/src/backend/optimizer/path/indxpath.c b/src/backend/optimizer/path/indxpath.c index 2a50272da6b..bcb1bc6097d 100644 --- a/src/backend/optimizer/path/indxpath.c +++ b/src/backend/optimizer/path/indxpath.c @@ -122,7 +122,6 @@ static Cost bitmap_and_cost_est(PlannerInfo *root, RelOptInfo *rel, List *paths); static PathClauseUsage *classify_index_clause_usage(Path *path, List **clauselist); -static Relids get_bitmap_tree_required_outer(Path *bitmapqual); static void find_indexpath_quals(Path *bitmapqual, List **quals, List **preds); static int find_list_position(Node *node, List **nodelist); static bool check_index_only(RelOptInfo *rel, IndexOptInfo *index); @@ -357,23 +356,16 @@ create_index_paths(PlannerInfo *root, RelOptInfo *rel) */ if (bitjoinpaths != NIL) { - List *path_outer; List *all_path_outers; ListCell *lc; - /* - * path_outer holds the parameterization of each path in bitjoinpaths - * (to save recalculating that several times), while all_path_outers - * holds all distinct parameterization sets. - */ - path_outer = all_path_outers = NIL; + /* Identify each distinct parameterization seen in bitjoinpaths */ + all_path_outers = NIL; foreach(lc, bitjoinpaths) { Path *path = (Path *) lfirst(lc); - Relids required_outer; + Relids required_outer = PATH_REQ_OUTER(path); - required_outer = get_bitmap_tree_required_outer(path); - path_outer = lappend(path_outer, required_outer); if (!bms_equal_any(required_outer, all_path_outers)) all_path_outers = lappend(all_path_outers, required_outer); } @@ -388,16 +380,14 @@ create_index_paths(PlannerInfo *root, RelOptInfo *rel) double loop_count; BitmapHeapPath *bpath; ListCell *lcp; - ListCell *lco; /* Identify all the bitmap join paths needing no more than that */ this_path_set = NIL; - forboth(lcp, bitjoinpaths, lco, path_outer) + foreach(lcp, bitjoinpaths) { Path *path = (Path *) lfirst(lcp); - Relids p_outers = (Relids) lfirst(lco); - if (bms_is_subset(p_outers, max_outers)) + if (bms_is_subset(PATH_REQ_OUTER(path), max_outers)) this_path_set = lappend(this_path_set, path); } @@ -411,7 +401,7 @@ create_index_paths(PlannerInfo *root, RelOptInfo *rel) bitmapqual = choose_bitmap_and(root, rel, this_path_set); /* And push that path into the mix */ - required_outer = get_bitmap_tree_required_outer(bitmapqual); + required_outer = PATH_REQ_OUTER(bitmapqual); loop_count = get_loop_count(root, rel->relid, required_outer); bpath = create_bitmap_heap_path(root, rel, bitmapqual, required_outer, loop_count, 0); @@ -1601,25 +1591,19 @@ path_usage_comparator(const void *a, const void *b) /* * Estimate the cost of actually executing a bitmap scan with a single - * index path (no BitmapAnd, at least not at this level; but it could be - * a BitmapOr). + * index path (which could be a BitmapAnd or BitmapOr node). */ static Cost bitmap_scan_cost_est(PlannerInfo *root, RelOptInfo *rel, Path *ipath) { BitmapHeapPath bpath; - Relids required_outer; - - /* Identify required outer rels, in case it's a parameterized scan */ - required_outer = get_bitmap_tree_required_outer(ipath); /* Set up a dummy BitmapHeapPath */ bpath.path.type = T_BitmapHeapPath; bpath.path.pathtype = T_BitmapHeapScan; bpath.path.parent = rel; bpath.path.pathtarget = rel->reltarget; - bpath.path.param_info = get_baserel_parampathinfo(root, rel, - required_outer); + bpath.path.param_info = ipath->param_info; bpath.path.pathkeys = NIL; bpath.bitmapqual = ipath; @@ -1628,10 +1612,13 @@ bitmap_scan_cost_est(PlannerInfo *root, RelOptInfo *rel, Path *ipath) * Parallel bitmap heap path will be considered at later stage. */ bpath.path.parallel_workers = 0; + + /* Now we can do cost_bitmap_heap_scan */ cost_bitmap_heap_scan(&bpath.path, root, rel, bpath.path.param_info, ipath, - get_loop_count(root, rel->relid, required_outer)); + get_loop_count(root, rel->relid, + PATH_REQ_OUTER(ipath))); return bpath.path.total_cost; } @@ -1643,46 +1630,15 @@ bitmap_scan_cost_est(PlannerInfo *root, RelOptInfo *rel, Path *ipath) static Cost bitmap_and_cost_est(PlannerInfo *root, RelOptInfo *rel, List *paths) { - BitmapAndPath apath; - BitmapHeapPath bpath; - Relids required_outer; - - /* Set up a dummy BitmapAndPath */ - apath.path.type = T_BitmapAndPath; - apath.path.pathtype = T_BitmapAnd; - apath.path.parent = rel; - apath.path.pathtarget = rel->reltarget; - apath.path.param_info = NULL; /* not used in bitmap trees */ - apath.path.pathkeys = NIL; - apath.bitmapquals = paths; - cost_bitmap_and_node(&apath, root); - - /* Identify required outer rels, in case it's a parameterized scan */ - required_outer = get_bitmap_tree_required_outer((Path *) &apath); - - /* Set up a dummy BitmapHeapPath */ - bpath.path.type = T_BitmapHeapPath; - bpath.path.pathtype = T_BitmapHeapScan; - bpath.path.parent = rel; - bpath.path.pathtarget = rel->reltarget; - bpath.path.param_info = get_baserel_parampathinfo(root, rel, - required_outer); - bpath.path.pathkeys = NIL; - bpath.bitmapqual = (Path *) &apath; + BitmapAndPath *apath; /* - * Check the cost of temporary path without considering parallelism. - * Parallel bitmap heap path will be considered at later stage. + * Might as well build a real BitmapAndPath here, as the work is slightly + * too complicated to be worth repeating just to save one palloc. */ - bpath.path.parallel_workers = 0; - - /* Now we can do cost_bitmap_heap_scan */ - cost_bitmap_heap_scan(&bpath.path, root, rel, - bpath.path.param_info, - (Path *) &apath, - get_loop_count(root, rel->relid, required_outer)); + apath = create_bitmap_and_path(root, rel, paths); - return bpath.path.total_cost; + return bitmap_scan_cost_est(root, rel, (Path *) apath); } @@ -1754,49 +1710,6 @@ classify_index_clause_usage(Path *path, List **clauselist) /* - * get_bitmap_tree_required_outer - * Find the required outer rels for a bitmap tree (index/and/or) - * - * We don't associate any particular parameterization with a BitmapAnd or - * BitmapOr node; however, the IndexPaths have parameterization info, in - * their capacity as standalone access paths. The parameterization required - * for the bitmap heap scan node is the union of rels referenced in the - * child IndexPaths. - */ -static Relids -get_bitmap_tree_required_outer(Path *bitmapqual) -{ - Relids result = NULL; - ListCell *lc; - - if (IsA(bitmapqual, IndexPath)) - { - return bms_copy(PATH_REQ_OUTER(bitmapqual)); - } - else if (IsA(bitmapqual, BitmapAndPath)) - { - foreach(lc, ((BitmapAndPath *) bitmapqual)->bitmapquals) - { - result = bms_join(result, - get_bitmap_tree_required_outer((Path *) lfirst(lc))); - } - } - else if (IsA(bitmapqual, BitmapOrPath)) - { - foreach(lc, ((BitmapOrPath *) bitmapqual)->bitmapquals) - { - result = bms_join(result, - get_bitmap_tree_required_outer((Path *) lfirst(lc))); - } - } - else - elog(ERROR, "unrecognized node type: %d", nodeTag(bitmapqual)); - - return result; -} - - -/* * find_indexpath_quals * * Given the Path structure for a plain or bitmap indexscan, extract lists |